mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-15 00:11:59 +00:00
ThearchyHelios
96af448fc5
- engine/judge.py：裁判的测试（test_judge_settings、test_verify_spend）换 judge._today 来模拟裁判这边跨天。上一版把它去掉、让三本账都只认 spend._today，等于改了这些测试的前提。改成裁判那本 Ledger 实例放在 judge.py（judge_spend，键不变，日历是 judge._today，它缺省就是 spend._today）；spend.py 只放核查、评测两本。test_evidence_judge 恢复原样，test_spend_ledger 跟着改：换 spend._today 三本一起滚，换 judge._today 只动裁判那本 - tools/datasource._store_schema：按 getattr 取 ctx.catalog_view——几处测试（和以后的调用方）直接拿一个只有 run_id / node_id 的对象调它，没有这个属性就是缺省视图
83 lines
4.0 KiB
Python
83 lines
4.0 KiB
Python
"""每日账泛化成 Ledger(key)（docs/design/next-round/01-效果度量与回归评测.md 做法 17）。
|
||
|
||
核查、裁判以前各写一份一模一样的「预留 → 找补 → 按本地日期滚动」，评测要是再抄一份就是第三份。现在三本账是同一个
|
||
Ledger 的三个实例，各记各的键、各管各的上限：一本触顶不挤占另外两本。裁判、核查原有的行为（模块级的 SPEND_KEY、
|
||
daily_spend、charge / settle）不变，已有的测试照旧守着；这里守账本本身和互不挤占。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import pytest
|
||
from sqlalchemy import delete
|
||
|
||
from app.db.base import SessionLocal
|
||
from app.db.models import Setting
|
||
from app.engine import judge, spend
|
||
from app.engine.judge import judge_spend
|
||
from app.engine.spend import Ledger, eval_spend, verify_spend
|
||
|
||
|
||
@pytest.fixture(autouse=True)
|
||
async def _clean():
|
||
keys = [verify_spend.key, judge_spend.key, eval_spend.key, "test_ledger"]
|
||
async with SessionLocal() as session:
|
||
await session.execute(delete(Setting).where(Setting.key.in_(keys)))
|
||
await session.commit()
|
||
yield
|
||
async with SessionLocal() as session:
|
||
await session.execute(delete(Setting).where(Setting.key.in_(keys)))
|
||
await session.commit()
|
||
|
||
|
||
def test_three_books_three_keys():
|
||
assert (verify_spend.key, judge_spend.key, eval_spend.key) == ("verify_spend", "judge_spend", "eval_spend")
|
||
# 老名字照旧指向各自那本：核查的模块函数、裁判的 SPEND_KEY / daily_spend
|
||
assert spend.SPEND_KEY == verify_spend.key
|
||
assert judge.SPEND_KEY == judge_spend.key
|
||
|
||
|
||
async def test_reserve_then_settle_and_the_limit():
|
||
book = Ledger("test_ledger")
|
||
day = await book.charge(0.4, limit=1.0, priced=True)
|
||
assert day is not None
|
||
assert await book.charge(0.7, limit=1.0, priced=True) is None, "加上这笔超过上限就不记"
|
||
await book.settle(day, -0.1)
|
||
got = await book.daily()
|
||
assert got["usd"] == pytest.approx(0.3) and got["calls"] == 1 and got["unpriced_calls"] == 0
|
||
# 估不出金额的照记次数，不比上限
|
||
assert await book.charge(0.0, limit=None, priced=False) is not None
|
||
assert (await book.daily())["unpriced_calls"] == 1
|
||
|
||
|
||
async def test_a_new_day_starts_from_zero():
|
||
day = {"today": "2026-09-28"}
|
||
book = Ledger("test_ledger", today=lambda: day["today"])
|
||
first = await book.charge(0.9, limit=1.0, priced=True)
|
||
assert first == "2026-09-28"
|
||
assert await book.charge(0.2, limit=1.0, priced=True) is None
|
||
day["today"] = "2026-09-29"
|
||
assert await book.charge(0.2, limit=1.0, priced=True) == "2026-09-29"
|
||
await book.settle(first, -0.5) # 跨了天的预留不找补：今天从零算
|
||
assert (await book.daily())["usd"] == pytest.approx(0.2)
|
||
|
||
|
||
async def test_one_book_hitting_its_cap_does_not_squeeze_the_others():
|
||
"""核查花光了当天的额度，裁判、评测照常记：三本账互不挤占。"""
|
||
assert await verify_spend.charge(2.0, limit=2.0, priced=True) is not None
|
||
assert await verify_spend.charge(0.01, limit=2.0, priced=True) is None
|
||
assert await judge_spend.charge(1.0, limit=2.0, priced=True) is not None
|
||
assert await eval_spend.charge(1.5, limit=2.0, priced=True) is not None
|
||
assert (await judge.daily_spend())["usd"] == pytest.approx(1.0)
|
||
assert (await spend.daily_spend())["usd"] == pytest.approx(2.0)
|
||
assert (await eval_spend.daily())["usd"] == pytest.approx(1.5)
|
||
|
||
|
||
async def test_all_books_roll_over_on_the_local_date(monkeypatch):
|
||
"""三本账按同一个本地日期滚动（spend._today）；裁判那本另留一个 judge._today，换它只动裁判这一本。"""
|
||
monkeypatch.setattr(spend, "_today", lambda: "2026-01-02")
|
||
assert await judge_spend.charge(0.1, limit=None, priced=True) == "2026-01-02"
|
||
assert (await judge.daily_spend())["date"] == "2026-01-02"
|
||
assert (await eval_spend.daily())["date"] == "2026-01-02"
|
||
monkeypatch.setattr(judge, "_today", lambda: "2026-01-03")
|
||
assert (await judge.daily_spend())["date"] == "2026-01-03"
|
||
assert (await verify_spend.daily())["date"] == "2026-01-02"
|